© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 18725
    Prev
    Next
    INDEX
    Explanations

    people currently/already

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     pred
    -0.09
    numer
    -0.09
    aja
    -0.09
    aji
    -0.09
    catch
    -0.08
    Numer
    -0.08
    urb
    -0.08
     citizen
    -0.08
     bog
    -0.08
    ayer
    -0.08
    POSITIVE LOGITS
     viewing
    0.13
     Viewing
    0.11
     âĺħ
    0.11
    uve
    0.11
     presently
    0.09
     trough
    0.09
     bidding
    0.09
    umbs
    0.09
     Thumb
    0.09
     currently
    0.09
    Activations Density 0.068%

    No Known Activations